CivArchive
    Preview 27884332
    Preview 27884338
    Preview 27884860
    Preview 27884868

    I found that images generated with my LoRA appear bit more amateur and less like the puppy "model_flux" style.

    In Better Faces, I aimed to include a diverse range of cultures and ethnicities—15 if I remember correctly—with both young and old subjects, currently focusing on women.

    aborigines, african, arab, arctic, brazilian, chinese, egyptian, finish, german, havaiian, indian, japanese, mongolian, russian, western

    my FLUX-lora responds to age prompts like __yo for 20yo, 30yo, 40yo.
    Weight: start with 0.3

    look image post for more, i was curious also negativ has an impact^^

    V........... see below ..............V

    Try my other face expression LoRA. If you use it at a weight of only 0.4 (without trigger words), you'll achieve more realistic results.

    https://civarchive.com/models/151594?modelVersionId=827638


    I aim for realistic faces with natural skin, avoiding perfect symmetry. :)

    FLUX with Euler-Sampler and SGM-Uniform-Scheduler performs well at -> 15-25 Steps

    Trigger words aren't essential but are useful for specifying cultural features! and "yo" ;)


    Model Descriptions:

    FLUXV3: new image set, new caption, 15 cultures, no permission to merge!

    FLUX: Recognizes mature (40yo) and young (20yo) subjects with reduced bokeh effect. For higher weights, it learns faces without jewelry, so consider adding jewelry and background details if desired.

    pony_weak: Better for close-ups; doesn't perform well with complex prompts. Not limited to "1girl" and includes backgrounds.

    pony_strong: works better with more complex prompts, not only 1girl, and call background

    face enhancer_v3: Stronger in close-ups. Please consider using my prompts. ;)

    face enhancer_v2: Much smoother and improved.


    Multi-Face Models:

    multifacesv_3: (Keywords: group, crowd, many faces) Generates more people, but distant faces still need improvement. Recommended weight: 0.3-0.8.

    multifaces_v2: (Trigger: specify the "number" of faces) i used also copax and juggernaut that is already not that bad at small faces so may you dont need it!

    multifaces_v1 -> (trigger: group, faces)


    Additional Recommendations:

    Overall, I suggest using Adetailer or a refiner for enhancing small faces.

    Face Swap with Adetailer and Reactor
    https://civarchive.com/articles/5002/face-swap-with-adetailer-and-reactor

    The new SDXL VAE (released on 2023.07.26) is significantly better than older versions for face generation.

    Please try my LoRA, and you'll often get more realistic faces—not those blurred, soft ones. ;)


    Hints:

    • please, almost no negative prompt is necessary!

    see my articles:
    https://civarchive.com/articles/1890/better-faces-lora
    https://civarchive.com/articles/1826/sdxl-prompts

    All SFW!

    Description

    less strong
    bit less bokeh
    less background change
    you can call 20yo, 30yo, 40yo
    more amateur like

    FAQ

    Comments (5)

    7016jayAlexNov 9, 2024· 8 reactions
    CivitAI

    hope the next version will include Persians (referring to Aryans in Iran) and Southeast Asians.

    There are only two ethnic groups in Asia: the Chinese and the Persians.

    The essence of the whole Southeast Asia is a mixture of Chinese and South Pacific blacks. And India is a mixed race of Persians and South Pacific blacks. The relationship between Arabia and Persia, like the relationship between Mongolia, South Korea, Japan, and China in Northeast Asia, appears to have the same skin color but very different facial features. Arabs, like Mongolians, have mixed too many genes from other ethnic groups, although it cannot be denied that there are pure blooded Mongolians and Arabs. Egyptians are not Arabs, they are brown people, and they are not black people from sub Saharan Africa.

    sevenof9247
    Author
    Nov 9, 2024

    I didn't mean to offend anyone!

    Maybe you'll get closer to the result if your request is “half Chinese and half Egyptian” or something similar

    7016jayAlexNov 9, 2024

    @sevenof9247 I found that it can not to generate people of different races in same frame, as they will be rendered as a unified race by the prompt words of a certain race. It is recommended to include photos of people of different races in the same frame in the training set for training.

    sevenof9247
    Author
    Nov 9, 2024

    @7016jayAlex you tryed a prompt like like "the blond haired woman on the right ... and the black woman on the left ..." FLUX has no pony-style prompt

    7016jayAlexNov 9, 2024· 1 reaction

    @sevenof9247 thanks your reminding,it works well

    LORA
    Flux.1 D

    Details

    Downloads
    2,769
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/5/2024
    Updated
    6/30/2026
    Deleted
    -
    Trigger Words:
    aborigines african arabian arctic brazilian chinese european havaiian japanese mongolian nordic russian western

    Available On (2 platforms)

    Same model published on other platforms. May have additional downloads or version variants.